Tensorflow 对象检测 API 仅显示损失值.如何获得mAP值? [英] Tensorflow Object Detection API only shows loss value. How to get mAP value?

问题描述

我正在使用 Tensorflow 对象检测 API 训练我自己的数据集.在训练时，我只得到损失值像这样.有没有办法在训练时或在张量板上获得 mAP 值?

I am training my own dataset using Tensorflow Object Detection API. While training, I only get loss value like this. Is there any way to get mAP value while training or on tensorboard ?

推荐答案

在 legacy/train.py 和 legacy/eval.py

in the legacy/train.py and legacy/eval.py

Example usage:
    ./train \
        --logtostderr \
        --train_dir=path/to/train_dir \
        --pipeline_config_path=pipeline_config.pbtxt

Example usage:
    ./eval \
        --logtostderr \
        --checkpoint_dir=path/to/checkpoint_dir \
        --eval_dir=path/to/eval_dir \
        --pipeline_config_path=pipeline_config_path.pbtxt \

对于一个终端，您使用 train.py 进行训练，

for one terminal you use train.py to train ,

对于另一个终端，您使用 eval.py 来评估，

for another terminal you use eval.py to evaluate ,

确保 train_dir 与 checkpoint_dir 和 eval_dir

另一个终端打开tensorboard

and the other terminal open up tensorboard

确保你安排好你的硬件设备，否则你可能无法同时打开train和eval

make sure u arrange ur hardware device, otherwise u might not able open both train and eval in the same time

这篇关于Tensorflow 对象检测 API 仅显示损失值.如何获得mAP值?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！